Hacker News Reader

Comment by DonsDiscountGas | Hacker News Reader

Not difficult at all. Just pick the approximate numbers you want and then introduce a random error of a few percent. (Normal, uniform, doesn't really matter). This is also not hard for statistics experts to detect, but it's much harder to prove (aka you've got plausible deniability).

One wonders why they didn't even bother to do fraud slightly better.

View on HN

If they can get away with being balatant, that is even more of a show of power.

Think of it this way - who has more power in a relationship? The one who is really good at cheating and hiding it? Or the the one who doesn’t even try to hide it, but suffers no consequences?

Just look at how many comments are trying to figure out how the numbers could be legitimate, and how unlikely it is that Maduro is going to actually be removed from power.

Unless done carefully this will almost certainly fail Benford’s Law.

Manipulating statistics is harder than you think.

It's my understanding that legitimate vote totals aren't likely to conform to Benford's law in the first place.

Even if that's the case, though, there might very well be other applicable tests this would run afoul of.

I’m not a statistician so I may be confusing it with Zipf’s law. But IIRC tallies from individual precincts should roughly conform to Benford’s law.

I think the concern is that precinct size tends to cluster in ways that mean results can cluster in ways that - for a large portion of the data - does not span a full order of magnitude.

To elaborate, if we imagine a polity with precincts that turn out 10,000 people each election, with two major party candidates that each get between 20% and 80% of the vote, we'd see precisely 0% precincts with a leading digit of 1, much less the ~30% predicted by Benford's law. Of course that doesn't exactly describe any real polity, but it doesn't seem surprising that real elections would be enough like that to screw with the pattern.

Precints have roughly even populations and therefore typically don't conform to Benford's law. https://www.youtube.com/watch?v=etx0k1nLn78&t=76s&pp=ygUQYmV...

> Unless done carefully this will almost certainly fail Benford’s Law.

IIRC Benford's law relies upon things that have power-law underpinnings, such as iterated growth% at different rates. In contrast, relative vote amounts at a given point in time don't have many ways to exhibit that, particularly when the total number of voters is fixed rather than having voters divide like bacteria during polling day.

However it might work if you were checking the growth in total eligible voters in different locations over time.

I like to imagine Benford's Law a bit like throwing randomly distributed darts through the air at a paper target, exept the target is graph paper with log-10 subdivisions. The "leading 1" zones are simply bigger targets. [0]

[0] https://commons.wikimedia.org/wiki/File:Logarithmic_scale.sv...

The Biden election in 2020 also failed Benford's law - unless you're suggesting that one was fake, it seems that failing Benford's law is okay.

There was a good paper in an American Statistical Association journal about this.

https://chance.amstat.org/2022/04/benfords-law-votes/

https://www.tandfonline.com/doi/abs/10.1080/09332480.2022.20...

Nobody is saying that failing a statistical test is by itself indicative of anything.

Statistically, yes they are. Immibis just did.

But votes aren’t tallied in one location, districts individually tally.

So now you’ve got to force each of those districts to change the numbers.

Reply on news.ycombinator.com